open-webui 0.3.31.dev1__tar.gz → 0.3.33.dev1__tar.gz

{open_webui-0.3.31.dev1 → open_webui-0.3.33.dev1}/CHANGELOG.md

@@ -5,6 +5,25 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.3.32] - 2024-10-06
+
+### Added
+
+- **🔢 Workspace Enhancements**: Added a display count for models, prompts, tools, and functions in the workspace, providing a clear overview and easier management.
+
+### Fixed
+
+- **🖥️ Web and YouTube Attachment Fix**: Resolved an issue where attaching web links and YouTube videos was malfunctioning, ensuring seamless integration and display within chats.
+- **📞 Call Mode Activation on Landing Page**: Fixed a bug where call mode was not operational from the landing page.
+
+### Changed
+
+- **🔄 URL Parameter Refinement**: Updated the 'tool_ids' URL parameter to 'tools' or 'tool-ids' for more intuitive and consistent user experience.
+- **🎨 Floating Buttons Styling Update**: Refactored the styling of floating buttons to intelligently adjust to the left side when there isn't enough room on the right, improving interface usability and aesthetic.
+- **🔧 Enhanced Accessibility for Floating Buttons**: Implemented the ability to close floating buttons with the 'Esc' key, making workflow smoother and more efficient for users navigating via keyboard.
+- **🖇️ Updated Information URL**: Information URLs now direct users to a general release page rather than a version-specific URL, ensuring access to the latest and relevant details all in one place.
+- **📦 Library Dependencies Update**: Upgraded dependencies to ensure compatibility and performance optimization for pip installs.
+
 ## [0.3.31] - 2024-10-06
 
 ### Added
@@ -23,6 +42,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - **🔍 Query Embedding**: Adjusted embedding behavior to enhance system performance by not repeating query embedding.
 - **💾 Lazy Load Optimizations**: Implemented lazy loading of large dependencies to minimize initial memory usage, boosting performance.
 - **🍏 Apple Touch Icon Support**: Optimizes the display of icons for web bookmarks on Apple mobile devices.
+- **🔽 Expandable Content Markdown Support**: Introducing 'details', 'summary' tag support for creating expandable content sections in markdown, facilitating cleaner, organized documentation and interactive content display.
 
 ### Fixed
 

{open_webui-0.3.31.dev1 → open_webui-0.3.33.dev1}/Dockerfile

@@ -1,6 +1,6 @@
 # syntax=docker/dockerfile:1
 # Initialize device type args
-# use build args in the docker build commmand with --build-arg="BUILDARG=true"
+# use build args in the docker build command with --build-arg="BUILDARG=true"
 ARG USE_CUDA=false
 ARG USE_OLLAMA=false
 # Tested with cu117 for CUDA 11 and cu121 for CUDA 12 (default)
@@ -11,6 +11,10 @@ ARG USE_CUDA_VER=cu121
 # IMPORTANT: If you change the embedding model (sentence-transformers/all-MiniLM-L6-v2) and vice versa, you aren't able to use RAG Chat with your previous documents loaded in the WebUI! You need to re-embed them.
 ARG USE_EMBEDDING_MODEL=sentence-transformers/all-MiniLM-L6-v2
 ARG USE_RERANKING_MODEL=""
+
+# Tiktoken encoding name; models to use can be found at https://huggingface.co/models?library=tiktoken
+ARG USE_TIKTOKEN_ENCODING_NAME="cl100k_base"
+
 ARG BUILD_HASH=dev-build
 # Override at your own risk - non-root configurations are untested
 ARG UID=0
@@ -72,6 +76,10 @@ ENV RAG_EMBEDDING_MODEL="$USE_EMBEDDING_MODEL_DOCKER" \
     RAG_RERANKING_MODEL="$USE_RERANKING_MODEL_DOCKER" \
     SENTENCE_TRANSFORMERS_HOME="/app/backend/data/cache/embedding/models"
 
+## Tiktoken model settings ##
+ENV TIKTOKEN_ENCODING_NAME="$USE_TIKTOKEN_ENCODING_NAME" \
+    TIKTOKEN_CACHE_DIR="/app/backend/data/cache/tiktoken"
+
 ## Hugging Face download cache ##
 ENV HF_HOME="/app/backend/data/cache/embedding/models"
 
@@ -131,11 +139,13 @@ RUN pip3 install uv && \
     uv pip install --system -r requirements.txt --no-cache-dir && \
     python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
     python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
+    python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
     else \
     pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu --no-cache-dir && \
     uv pip install --system -r requirements.txt --no-cache-dir && \
     python -c "import os; from sentence_transformers import SentenceTransformer; SentenceTransformer(os.environ['RAG_EMBEDDING_MODEL'], device='cpu')" && \
     python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='cpu', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"; \
+    python -c "import os; import tiktoken; tiktoken.get_encoding(os.environ['TIKTOKEN_ENCODING_NAME'])"; \
     fi; \
     chown -R $UID:$GID /app/backend/data/
 

{open_webui-0.3.31.dev1 → open_webui-0.3.33.dev1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: open-webui
-Version: 0.3.31.dev1
+Version: 0.3.33.dev1
 Summary: Open WebUI
 Author-email: Timothy Jaeryang Baek <tim@openwebui.com>
 License: MIT License
@@ -32,11 +32,12 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Topic :: Communications :: Chat
 Classifier: Topic :: Multimedia
 Requires-Python: <3.12.0a1,>=3.11
-Requires-Dist: aiohttp==3.10.5
+Requires-Dist: aiohttp==3.10.8
 Requires-Dist: alembic==1.13.2
 Requires-Dist: anthropic
 Requires-Dist: apscheduler==3.10.4
 Requires-Dist: argon2-cffi==23.1.0
+Requires-Dist: async-timeout
 Requires-Dist: authlib==1.3.2
 Requires-Dist: bcrypt==4.2.0
 Requires-Dist: black==24.8.0
@@ -45,7 +46,7 @@ Requires-Dist: chromadb==0.5.9
 Requires-Dist: colbert-ai==0.2.21
 Requires-Dist: docker~=7.1.0
 Requires-Dist: docx2txt==0.8
-Requires-Dist: duckduckgo-search~=6.2.11
+Requires-Dist: duckduckgo-search~=6.2.13
 Requires-Dist: einops==0.8.0
 Requires-Dist: extract-msg
 Requires-Dist: fake-useragent==1.5.1
@@ -56,7 +57,8 @@ Requires-Dist: flask==3.0.3
 Requires-Dist: fpdf2==2.7.9
 Requires-Dist: ftfy==6.2.3
 Requires-Dist: google-generativeai==0.7.2
-Requires-Dist: langchain-chroma==0.1.2
+Requires-Dist: googleapis-common-protos==1.63.2
+Requires-Dist: langchain-chroma==0.1.4
 Requires-Dist: langchain-community==0.2.12
 Requires-Dist: langchain==0.2.15
 Requires-Dist: langfuse==2.44.0
@@ -65,22 +67,23 @@ Requires-Dist: nltk==3.9.1
 Requires-Dist: openai
 Requires-Dist: opencv-python-headless==4.10.0.84
 Requires-Dist: openpyxl==3.1.5
-Requires-Dist: pandas==2.2.2
+Requires-Dist: pandas==2.2.3
 Requires-Dist: passlib[bcrypt]==1.7.4
 Requires-Dist: peewee-migrate==1.12.2
 Requires-Dist: peewee==3.17.6
 Requires-Dist: psutil
 Requires-Dist: psycopg2-binary==2.9.9
-Requires-Dist: pydantic==2.8.2
+Requires-Dist: pydantic==2.9.2
 Requires-Dist: pydub
 Requires-Dist: pyjwt[crypto]==2.9.0
+Requires-Dist: pymdown-extensions==10.11.2
 Requires-Dist: pymilvus==2.4.7
 Requires-Dist: pymongo
 Requires-Dist: pymysql==1.1.1
 Requires-Dist: pypandoc==1.13
 Requires-Dist: pypdf==4.3.1
 Requires-Dist: pytest-docker~=3.1.1
-Requires-Dist: pytest~=8.2.2
+Requires-Dist: pytest~=8.3.2
 Requires-Dist: python-jose==3.3.0
 Requires-Dist: python-multipart==0.0.9
 Requires-Dist: python-pptx==1.0.0
@@ -91,12 +94,13 @@ Requires-Dist: rank-bm25==0.2.2
 Requires-Dist: rapidocr-onnxruntime==1.3.24
 Requires-Dist: redis
 Requires-Dist: requests==2.32.3
-Requires-Dist: sentence-transformers==3.0.1
+Requires-Dist: sentence-transformers==3.2.0
 Requires-Dist: sqlalchemy==2.0.32
 Requires-Dist: tiktoken
 Requires-Dist: unstructured==0.15.9
 Requires-Dist: uvicorn[standard]==0.30.6
 Requires-Dist: validators==0.33.0
+Requires-Dist: xhtml2pdf==0.2.16
 Requires-Dist: xlrd==2.0.1
 Requires-Dist: youtube-transcript-api==0.6.2
 Description-Content-Type: text/markdown

{open_webui-0.3.31.dev1 → open_webui-0.3.33.dev1}/TROUBLESHOOTING.md

@@ -18,7 +18,7 @@ If you're experiencing connection issues, it’s often due to the WebUI docker c
 docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=http://127.0.0.1:11434 --name open-webui --restart always ghcr.io/open-webui/open-webui:main
 ```
 
-### Error on Slow Reponses for Ollama
+### Error on Slow Responses for Ollama
 
 Open WebUI has a default timeout of 5 minutes for Ollama to finish generating the response. If needed, this can be adjusted via the environment variable AIOHTTP_CLIENT_TIMEOUT, which sets the timeout in seconds.
 

{open_webui-0.3.31.dev1 → open_webui-0.3.33.dev1}/backend/open_webui/apps/audio/main.py

@@ -63,6 +63,9 @@ app.state.config.STT_OPENAI_API_KEY = AUDIO_STT_OPENAI_API_KEY
 app.state.config.STT_ENGINE = AUDIO_STT_ENGINE
 app.state.config.STT_MODEL = AUDIO_STT_MODEL
 
+app.state.config.WHISPER_MODEL = WHISPER_MODEL
+app.state.faster_whisper_model = None
+
 app.state.config.TTS_OPENAI_API_BASE_URL = AUDIO_TTS_OPENAI_API_BASE_URL
 app.state.config.TTS_OPENAI_API_KEY = AUDIO_TTS_OPENAI_API_KEY
 app.state.config.TTS_ENGINE = AUDIO_TTS_ENGINE
@@ -82,6 +85,31 @@ SPEECH_CACHE_DIR = Path(CACHE_DIR).joinpath("./audio/speech/")
 SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
 
 
+def set_faster_whisper_model(model: str, auto_update: bool = False):
+    if model and app.state.config.STT_ENGINE == "":
+        from faster_whisper import WhisperModel
+
+        faster_whisper_kwargs = {
+            "model_size_or_path": model,
+            "device": whisper_device_type,
+            "compute_type": "int8",
+            "download_root": WHISPER_MODEL_DIR,
+            "local_files_only": not auto_update,
+        }
+
+        try:
+            app.state.faster_whisper_model = WhisperModel(**faster_whisper_kwargs)
+        except Exception:
+            log.warning(
+                "WhisperModel initialization failed, attempting download with local_files_only=False"
+            )
+            faster_whisper_kwargs["local_files_only"] = False
+            app.state.faster_whisper_model = WhisperModel(**faster_whisper_kwargs)
+
+    else:
+        app.state.faster_whisper_model = None
+
+
 class TTSConfigForm(BaseModel):
     OPENAI_API_BASE_URL: str
     OPENAI_API_KEY: str
@@ -99,6 +127,7 @@ class STTConfigForm(BaseModel):
     OPENAI_API_KEY: str
     ENGINE: str
     MODEL: str
+    WHISPER_MODEL: str
 
 
 class AudioConfigUpdateForm(BaseModel):
@@ -152,6 +181,7 @@ async def get_audio_config(user=Depends(get_admin_user)):
             "OPENAI_API_KEY": app.state.config.STT_OPENAI_API_KEY,
             "ENGINE": app.state.config.STT_ENGINE,
             "MODEL": app.state.config.STT_MODEL,
+            "WHISPER_MODEL": app.state.config.WHISPER_MODEL,
         },
     }
 
@@ -176,6 +206,8 @@ async def update_audio_config(
     app.state.config.STT_OPENAI_API_KEY = form_data.stt.OPENAI_API_KEY
     app.state.config.STT_ENGINE = form_data.stt.ENGINE
     app.state.config.STT_MODEL = form_data.stt.MODEL
+    app.state.config.WHISPER_MODEL = form_data.stt.WHISPER_MODEL
+    set_faster_whisper_model(form_data.stt.WHISPER_MODEL, WHISPER_MODEL_AUTO_UPDATE)
 
     return {
         "tts": {
@@ -194,6 +226,7 @@ async def update_audio_config(
             "OPENAI_API_KEY": app.state.config.STT_OPENAI_API_KEY,
             "ENGINE": app.state.config.STT_ENGINE,
             "MODEL": app.state.config.STT_MODEL,
+            "WHISPER_MODEL": app.state.config.WHISPER_MODEL,
         },
     }
 
@@ -367,27 +400,10 @@ def transcribe(file_path):
     id = filename.split(".")[0]
 
     if app.state.config.STT_ENGINE == "":
-        from faster_whisper import WhisperModel
-
-        whisper_kwargs = {
-            "model_size_or_path": WHISPER_MODEL,
-            "device": whisper_device_type,
-            "compute_type": "int8",
-            "download_root": WHISPER_MODEL_DIR,
-            "local_files_only": not WHISPER_MODEL_AUTO_UPDATE,
-        }
-
-        log.debug(f"whisper_kwargs: {whisper_kwargs}")
-
-        try:
-            model = WhisperModel(**whisper_kwargs)
-        except Exception:
-            log.warning(
-                "WhisperModel initialization failed, attempting download with local_files_only=False"
-            )
-            whisper_kwargs["local_files_only"] = False
-            model = WhisperModel(**whisper_kwargs)
+        if app.state.faster_whisper_model is None:
+            set_faster_whisper_model(app.state.config.WHISPER_MODEL)
 
+        model = app.state.faster_whisper_model
         segments, info = model.transcribe(file_path, beam_size=5)
         log.info(
             "Detected language '%s' with probability %f"
@@ -395,7 +411,6 @@ def transcribe(file_path):
         )
 
         transcript = "".join([segment.text for segment in list(segments)])
-
         data = {"text": transcript.strip()}
 
         # save the transcript to a json file
@@ -403,7 +418,7 @@ def transcribe(file_path):
         with open(transcript_file, "w") as f:
             json.dump(data, f)
 
-        print(data)
+        log.debug(data)
         return data
     elif app.state.config.STT_ENGINE == "openai":
         if is_mp4_audio(file_path):
@@ -417,7 +432,7 @@ def transcribe(file_path):
         files = {"file": (filename, open(file_path, "rb"))}
         data = {"model": app.state.config.STT_MODEL}
 
-        print(files, data)
+        log.debug(files, data)
 
         r = None
         try:
@@ -450,7 +465,7 @@ def transcribe(file_path):
                 except Exception:
                     error_detail = f"External: {e}"
 
-            raise error_detail
+            raise Exception(error_detail)
 
 
 @app.post("/transcriptions")

{open_webui-0.3.31.dev1 → open_webui-0.3.33.dev1}/backend/open_webui/apps/images/utils/comfyui.py

@@ -125,22 +125,34 @@ async def comfyui_generate_image(
                     workflow[node_id]["inputs"][node.key] = model
             elif node.type == "prompt":
                 for node_id in node.node_ids:
-                    workflow[node_id]["inputs"]["text"] = payload.prompt
+                    workflow[node_id]["inputs"][
+                        node.key if node.key else "text"
+                    ] = payload.prompt
             elif node.type == "negative_prompt":
                 for node_id in node.node_ids:
-                    workflow[node_id]["inputs"]["text"] = payload.negative_prompt
+                    workflow[node_id]["inputs"][
+                        node.key if node.key else "text"
+                    ] = payload.negative_prompt
             elif node.type == "width":
                 for node_id in node.node_ids:
-                    workflow[node_id]["inputs"]["width"] = payload.width
+                    workflow[node_id]["inputs"][
+                        node.key if node.key else "width"
+                    ] = payload.width
             elif node.type == "height":
                 for node_id in node.node_ids:
-                    workflow[node_id]["inputs"]["height"] = payload.height
+                    workflow[node_id]["inputs"][
+                        node.key if node.key else "height"
+                    ] = payload.height
             elif node.type == "n":
                 for node_id in node.node_ids:
-                    workflow[node_id]["inputs"]["batch_size"] = payload.n
+                    workflow[node_id]["inputs"][
+                        node.key if node.key else "batch_size"
+                    ] = payload.n
             elif node.type == "steps":
                 for node_id in node.node_ids:
-                    workflow[node_id]["inputs"]["steps"] = payload.steps
+                    workflow[node_id]["inputs"][
+                        node.key if node.key else "steps"
+                    ] = payload.steps
             elif node.type == "seed":
                 seed = (
                     payload.seed

{open_webui-0.3.31.dev1 → open_webui-0.3.33.dev1}/backend/open_webui/apps/ollama/main.py

@@ -547,8 +547,8 @@ class GenerateEmbeddingsForm(BaseModel):
 
 class GenerateEmbedForm(BaseModel):
     model: str
-    input: str
-    truncate: Optional[bool]
+    input: list[str] | str
+    truncate: Optional[bool] = None
     options: Optional[dict] = None
     keep_alive: Optional[Union[int, str]] = None
 
@@ -560,48 +560,7 @@ async def generate_embeddings(
     url_idx: Optional[int] = None,
     user=Depends(get_verified_user),
 ):
-    if url_idx is None:
-        model = form_data.model
-
-        if ":" not in model:
-            model = f"{model}:latest"
-
-        if model in app.state.MODELS:
-            url_idx = random.choice(app.state.MODELS[model]["urls"])
-        else:
-            raise HTTPException(
-                status_code=400,
-                detail=ERROR_MESSAGES.MODEL_NOT_FOUND(form_data.model),
-            )
-
-    url = app.state.config.OLLAMA_BASE_URLS[url_idx]
-    log.info(f"url: {url}")
-
-    r = requests.request(
-        method="POST",
-        url=f"{url}/api/embed",
-        headers={"Content-Type": "application/json"},
-        data=form_data.model_dump_json(exclude_none=True).encode(),
-    )
-    try:
-        r.raise_for_status()
-
-        return r.json()
-    except Exception as e:
-        log.exception(e)
-        error_detail = "Open WebUI: Server Connection Error"
-        if r is not None:
-            try:
-                res = r.json()
-                if "error" in res:
-                    error_detail = f"Ollama: {res['error']}"
-            except Exception:
-                error_detail = f"Ollama: {e}"
-
-        raise HTTPException(
-            status_code=r.status_code if r else 500,
-            detail=error_detail,
-        )
+    return generate_ollama_batch_embeddings(form_data, url_idx)
 
 
 @app.post("/api/embeddings")
@@ -611,6 +570,15 @@ async def generate_embeddings(
     url_idx: Optional[int] = None,
     user=Depends(get_verified_user),
 ):
+    return generate_ollama_embeddings(form_data=form_data, url_idx=url_idx)
+
+
+def generate_ollama_embeddings(
+    form_data: GenerateEmbeddingsForm,
+    url_idx: Optional[int] = None,
+):
+    log.info(f"generate_ollama_embeddings {form_data}")
+
     if url_idx is None:
         model = form_data.model
 
@@ -637,7 +605,14 @@ async def generate_embeddings(
     try:
         r.raise_for_status()
 
-        return r.json()
+        data = r.json()
+
+        log.info(f"generate_ollama_embeddings {data}")
+
+        if "embedding" in data:
+            return data
+        else:
+            raise Exception("Something went wrong :/")
     except Exception as e:
         log.exception(e)
         error_detail = "Open WebUI: Server Connection Error"
@@ -655,11 +630,11 @@ async def generate_embeddings(
         )
 
 
-def generate_ollama_embeddings(
-    form_data: GenerateEmbeddingsForm,
+def generate_ollama_batch_embeddings(
+    form_data: GenerateEmbedForm,
     url_idx: Optional[int] = None,
 ):
-    log.info(f"generate_ollama_embeddings {form_data}")
+    log.info(f"generate_ollama_batch_embeddings {form_data}")
 
     if url_idx is None:
         model = form_data.model
@@ -680,7 +655,7 @@ def generate_ollama_embeddings(
 
     r = requests.request(
         method="POST",
-        url=f"{url}/api/embeddings",
+        url=f"{url}/api/embed",
         headers={"Content-Type": "application/json"},
         data=form_data.model_dump_json(exclude_none=True).encode(),
     )
@@ -689,10 +664,10 @@ def generate_ollama_embeddings(
 
         data = r.json()
 
-        log.info(f"generate_ollama_embeddings {data}")
+        log.info(f"generate_ollama_batch_embeddings {data}")
 
-        if "embedding" in data:
-            return data["embedding"]
+        if "embeddings" in data:
+            return data
         else:
             raise Exception("Something went wrong :/")
     except Exception as e:
@@ -788,8 +763,7 @@ async def generate_chat_completion(
     user=Depends(get_verified_user),
 ):
     payload = {**form_data.model_dump(exclude_none=True)}
-    log.debug(f"{payload = }")
-
+    log.debug(f"generate_chat_completion() - 1.payload = {payload}")
     if "metadata" in payload:
         del payload["metadata"]
 
@@ -824,7 +798,7 @@ async def generate_chat_completion(
 
     url = get_ollama_url(url_idx, payload["model"])
     log.info(f"url: {url}")
-    log.debug(payload)
+    log.debug(f"generate_chat_completion() - 2.payload = {payload}")
 
     return await post_streaming_url(
         f"{url}/api/chat",

{open_webui-0.3.31.dev1 → open_webui-0.3.33.dev1}/backend/open_webui/apps/openai/main.py

@@ -18,7 +18,10 @@ from open_webui.config import (
     OPENAI_API_KEYS,
     AppConfig,
 )
-from open_webui.env import AIOHTTP_CLIENT_TIMEOUT
+from open_webui.env import (
+    AIOHTTP_CLIENT_TIMEOUT,
+    AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST,
+)
 
 from open_webui.constants import ERROR_MESSAGES
 from open_webui.env import SRC_LOG_LEVELS
@@ -179,7 +182,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
 
 
 async def fetch_url(url, key):
-    timeout = aiohttp.ClientTimeout(total=3)
+    timeout = aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST)
     try:
         headers = {"Authorization": f"Bearer {key}"}
         async with aiohttp.ClientSession(timeout=timeout, trust_env=True) as session:
@@ -237,9 +240,7 @@ def merge_models_lists(model_lists):
 
 
 def is_openai_api_disabled():
-    api_keys = app.state.config.OPENAI_API_KEYS
-    no_keys = len(api_keys) == 1 and api_keys[0] == ""
-    return no_keys or not app.state.config.ENABLE_OPENAI_API
+    return not app.state.config.ENABLE_OPENAI_API
 
 
 async def get_all_models_raw() -> list: